Papers by Fumiyo Fukumoto
Exploiting Labeled and Unlabeled Data via Transformer Fine-tuning for Peer-Review Score Prediction (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on automatic peer-review aspect score prediction rely on limited data sets. |
| Approach: | They propose a semi-supervised learning method that incorporates the Transformer fine-tuning into the -model to leverage contextual features from unlabeled data. |
| Outcome: | The proposed method outperforms supervised and naive methods in the peer-review dataset. |
Text Categorization by Learning Predominant Sense of Words as Auxiliary Task (P19-1)
Copied to clipboard
| Challenge: | Existing methods for text categorization use implicit representations to learn the senses of words. |
| Approach: | They propose a method for text categorization by leveraging the predominant sense of words depending on the domain. |
| Outcome: | The proposed model improves performance on four benchmark datasets. |
Multi-task Learning for Automated Essay Scoring with Sentiment Analysis (2020.aacl-srw)
Copied to clipboard
| Challenge: | Automated Essay Scoring (AES) is a process that aims to alleviate the workload of graders and improve the feedback cycle in educational systems. |
| Approach: | They propose to combine two tasks, sentiment analysis and AES by utilizing multi-task learning to combine sentiment features extracted from opinion expressions. |
| Outcome: | The proposed model produces a QWK of 0.763 on the Automated StudentAssessment Prize (ASAP) benchmark. |
A Dataset of Crowdsourced Word Sequences: Collections and Answer Aggregation for Ground Truth Creation (D19-59)
Copied to clipboard
| Challenge: | Existing work on answer aggregation for labels is limited . existing work on label aggregations is limited to label . |
| Approach: | They propose three approaches to extractive word sequence aggregation from translated sentences generated by multiple workers. |
| Outcome: | The proposed dataset contains translated sentences generated from multiple workers. |
Aspect-Category Enhanced Learning with a Neural Coherence Model for Implicit Sentiment Analysis (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis (ABSA) is a major research topic in NLP since social networking services have increased . but the recognition of implicit sentiments that do not contain obvious opinion words remains unexplored . elcom captures document-level coherence by using contrastive learning and sentence-level by a hypergraph . |
| Approach: | They propose aspect-category enhanced learning with a neural coherence model . it captures document-level coherency by contrastive learning and sentence-level by a hypergraph . |
| Outcome: | The proposed model captures document-level coherence by using contrastive learning and sentence-level by a hypergraph to mine opinions from explicit sentences to aid implicit sentiment classification. |
HFT-CNN: Learning Hierarchical Category Structure for Multi-label Short Text Categorization (D18-1)
Copied to clipboard
| Challenge: | Existing methods for categorization of short texts use non-hierarchical flat model, but they are limited by domain-independent knowledge distribution. |
| Approach: | They propose a method which leverages hierarchical relationships between pre-defined categories to tackle the data sparsity problem. |
| Outcome: | The proposed method is competitive with the state-of-the-art methods on a multi-label categorization task for short texts using two benchmark datasets. |
HSCNN: A Hybrid-Siamese Convolutional Neural Network for Extremely Imbalanced Multi-label Text Classification (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to solve the data imbalance problem are limited in extremely imbalanced data. |
| Approach: | They propose a hybrid approach which adapts general networks for head categories and few-shot techniques for tail categories. |
| Outcome: | The proposed approach improves the performance of Single networks with diverse loss objectives on tail or entire categories. |
Causal Denoising Prototypical Network for Few-Shot Multi-label Aspect Category Detection (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent methods that learn robust prototypes to represent aspects with limited support samples address noise categories in the support set that hinder their models from effective prototype generation. |
| Approach: | They propose a causal denoising prototypical network for few-shot MACD by learning robust prototypes to represent categories with limited support samples. |
| Outcome: | The proposed model outperforms baseline models and can prevent models from overly predicting more categories and mitigate semantic ambiguity issues among categories. |
FL-MSCL: A Unified Figurative Language Detection Model Driven by Multi-Type Signals and Contrastive Learning (2026.acl-short)
Copied to clipboard
| Challenge: | Figurative language recognition challenges distinguishing between fine-grained rhetorical categories . existing approaches are framed as single-category binary classifiers . |
| Approach: | They propose a framework that integrates prompt-based knowledge injection with supervised contrastive learning to enforce explicit class distinctions. |
| Outcome: | The proposed framework achieves competitive performance on a four-way sentence-level classification task. |
Enhancing High-order Interaction Awareness in LLM-based Recommender Model (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to model user-item interactions do not account for high-order interactions. |
| Approach: | They propose to enhance whole-word embeddings to enhance LLMs’ interpretation of graph-constructed interactions for recommendations without requiring graph pre-training. |
| Outcome: | The proposed model outperforms state-of-the-art methods in direct recommendations. |
A Neural Local Coherence Analysis Model for Clarity Text Scoring (2020.coling-main)
Copied to clipboard
| Challenge: | Existing methods for scoring text clarity use local coherence between adjacent sentences . local cohesion is one of the main properties to identify whether a text is well-structured or not. |
| Approach: | They propose a method for scoring text clarity by utilizing local coherence between adjacent sentences. |
| Outcome: | The proposed method improves on the PeerRead benchmark dataset. |
AGRec: Adapting Autoregressive Decoders with Graph Reasoning for LLM-based Sequential Recommendation (2025.findings-acl)
Copied to clipboard
| Challenge: | Autoregressive decoders in large language models excel at capturing sequential behaviors for generative recommendations, but they lack graph-structured user-item interactions, which are widely recognized as beneficial. |
| Approach: | They propose a novel algorithm that adapts LLMs’ decoders with graph reasoning for recommendation by augmenting the decoding logits with an auxiliary GNN model to optimize token generation. |
| Outcome: | The proposed model outperforms state-of-the-art models in sequential recommendations. |
Enhanced Coherence-Aware Network with Hierarchical Disentanglement for Aspect-Category Sentiment Analysis (2024.lrec-main)
Copied to clipboard
| Challenge: | Aspect-category-based sentiment analysis (ACSA) is a popular approach for identifying aspect categories and predicting their sentiments. |
| Approach: | They propose an enhanced coherence-aware network with hierarchical disentanglement (ECAN) to capture contexts across the whole review and to help the implicit aspect and sentiment identification. |
| Outcome: | The proposed network decouples multiple aspects and sentiment features and achieves state-of-the-art (SOTA) performance. |
Abstract, Rationale, Stance: A Joint Model for Scientific Claim Verification (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing scientific claim verification models have problems of error propagation among modules and lack of sharing valuable information among modules. |
| Approach: | They propose an approach that jointly learns the modules for the three tasks with a machine reading comprehension framework by including claim information. |
| Outcome: | The proposed approach outperforms existing models on the SciFact dataset on the three tasks of abstract retrieval, rationale selection and stance prediction. |
RDRec: Rationale Distillation for LLM-based Recommendation (2024.acl-short)
Copied to clipboard
| Challenge: | Existing models that bridge users and items through textual prompts for effective semantic reasoning do not consider the underlying rationales behind interactions, such as user preferences and item attributes. |
| Approach: | They propose a rationale distillation recommender model that learns rationales generated by a larger language model (LM) by leveraging reviews related to users and items. |
| Outcome: | The proposed model achieves state-of-the-art (SOTA) performance in top-N and sequential recommendations. |
Semi-Automatic Construction and Refinement of an Annotated Corpus for a Deep Learning Framework for Emotion Classification (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing methods for emotion classification are expensive and require a large corpus of data. |
| Approach: | They propose a method for creating a semi-automatically constructed emotion corpus by correcting errors in the corpus. |
| Outcome: | The proposed method improves the quality of the emotion labels by correcting errors. |
Claim veracity assessment for explainable fake news detection (2025.coling-main)
Copied to clipboard
| Challenge: | Recent approaches to fake news detection focus on textual features without external facts, which may lead to a misrepresentation of the truth. |
| Approach: | They propose a new fake news detection method that predicts the truth or false-hood of a claim based on relevant factual evidence or LLM’s inference mechanisms. |
| Outcome: | The proposed method produces the final synthesized prediction, along with well-founded facts or reasoning. |